Semantic segmentation with millions of features: integrating multiple cues in a combined random forest approach

Authors:
Björn Fröhlich;Erik Rodner;Joachim Denzler
Affiliations:
Computer Vision Group, Friedrich Schiller University Jena, Germany;Computer Vision Group, Friedrich Schiller University Jena, Germany;Computer Vision Group, Friedrich Schiller University Jena, Germany
Venue:
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part I
Year:
2012

Citing 12
Cited 1

Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Random Forests

Machine Learning
Robust Real-Time Face Detection

International Journal of Computer Vision
Efficient Graph-Based Image Segmentation

International Journal of Computer Vision
Geometric Context from a Single Image

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Evaluation of Structure Recognition Using Labelled Facade Images

Proceedings of the 31st DAGM Symposium on Pattern Recognition
Auto-Context and Its Application to High-Level Vision Tasks and 3D Brain Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Fast Approach for Pixelwise Labeling of Facade Images

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
An Efficient Approach to Semantic Segmentation

International Journal of Computer Vision
Regionwise classification of building facade images

PIA'11 Proceedings of the 2011 ISPRS conference on Photogrammetric image analysis
TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
A three-layered approach to facade parsing

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VII

Building facade detection, segmentation, and parameter estimation for mobile robot stereo vision

Image and Vision Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a new combined approach for feature extraction, classification, and context modeling in an iterative framework based on random decision trees and a huge amount of features. A major focus of this paper is to integrate different kinds of feature types like color, geometric context, and auto context features in a joint, flexible and fast manner. Furthermore, we perform an in-depth analysis of multiple feature extraction methods and different feature types. Extensive experiments are performed on challenging facade recognition datasets, where we show that our approach significantly outperforms previous approaches with a performance gain of more than 15% on the most difficult dataset.